Abstract not found

In a typical file system, only the current version of a file (or directory) is available. In Wayback, a user can also access any previous version, all the way back to the file’s creation time. Versioning is done automatically at the write level: each write to the file creates a new version. Wayback implements versioning using an undo log structure, exploiting the massive space available on modern disks to provide its very useful functionality. Wayback is a userlevel file system built on the FUSE framework that relies on an underlying file system for access to the disk. In addition to simplifying Wayback, this also allows it to extend any existing file system with versioning: after being mounted, the file system can be mounted a second time with versioning. We describe the implementation of Wayback, and evaluate its performance using several benchmarks. 1

In this paper, we present an approach for realizing a safe execution environment (SEE) that enables users to “try out” new software (or configuration changes to existing software) without the fear of damaging the system in any manner. A key property of our SEE is that it faithfully reproduces the behavior of applications, as if they were running natively on the underlying host operating system. This is accomplished via one-way isolation: processes running within the SEE are given read-access to the environment provided by the host OS, but their write operations are prevented from escaping outside the SEE. As a result, SEE processes cannot impact the behavior of host OS processes, or the integrity of data on the host OS. Our SEE supports a wide range of tasks, including: study of malicious code, controlled execution of untrusted software, experimentation with software configuration changes, testing of software patches, and so on. It provides a convenient way for users to inspect system changes made within the SEE. If the user does not accept these changes, they can be rolled back at the click of a button. Otherwise, the changes can be “committed ” so as to become visible outside the SEE. We provide consistency criteria that ensure semantic consistency of the committed results. We also develop an efficient technique for implementing the commit operation. Our implementation results show that most software, including fairly complex server and client applications, can run successfully within the SEE. The approach introduces low performance overheads, typically below 10%.

Automatic provenance collection describes systems that observe processes and data transformations inferring, collecting, and maintaining provenance about them. Automatic collection is a powerful tool for analysis of objects and processes, providing a level of transparency and pervasiveness not found in more conventional provenance systems. Unfortunately, automatic collection is also difficult. We discuss the challenges we encountered and the issues we exposed as we developed an automatic provenance collector that runs at the operating system level.

Abstract: This is a position paper on multi-tenant databases. As motivation, it first describes the emerging marketplace of hosted enterprise services and the importance of using multi-tenancy to handle high traffic volumes at low cost. It then outlines the main requirements on multi-tenant databases: scale up by consolidating multiple tenants onto the same server and scale out by providing an administrative framework that manages a farm of such servers. Finally it describes three approaches to implementing multi-tenant databases and compares them based on some simple experiments. The main conclusion is that existing database vendors need to enhance their products to better support multi-tenancy. 1 Hosted Services and Multi-Tenancy In the hosted service model [GM02a, GM02b, Wa03], a service provider develops an application and operates the system that hosts it. Customers access the application over the Internet using industry-standard web browsers or Web Services clients. As the Internet has matured, hosted services have appeared for an increasingly wide variety of enterprise applications, including ones that manage sales, marketing, support, human resources, planning, manufacturing, inventory, financials, purchasing, and compliance [Th06]. While hosted services are attractive to all segments of the market, they are particularly appealing to small- to mediumsized businesses, which often lack the resources to maintain a complex data center. Hosted services are

Hard disks contain data—frequently an irreplaceable asset of high monetary and non-monetary value. At the same time, hard disks are mechanical devices that consume power, are noisy, and fragile when their platters are rotating. In this paper we demonstrate that hard disks cause different kinds of problems for different types of computer systems and demystify several common misconceptions. We show that solutions developed to date are incapable of solving the power consumption, noise, and data reliability problems without sacrificing hard disk life-time, data reliability, or user convenience. We considered data reliability, recovery, performance, user convenience, and hard disk-caused problems together at the enterprise scale. We have designed GreenFS: a fan-out stackable file system that offers all-time all-data run-time data protection, improves performance under typical user workloads, and allows hard disks to be kept off most of the time. As a result, GreenFS improves enterprise data protection, minimizes disk drive-related power consumption and noise and increases the chances of disk drive survivability in case of unexpected external impacts.

A new generation of storage systems exploit decreasing storage costs to allow applications to take snapshots of past states and retain them for long durations. Over time, current snapshot techniques can produce large volumes of snapshots. Indiscriminately keeping all snapshots accessible is impractical, even if raw disk storage is cheap, because administering such large-volume storage is expensive over a long duration. Moreover, not all snapshots are equally valuable. Thresher is a new snapshot storage management system, based on novel copyon-write snapshot techniques, that is the first to provide applications the ability to discriminate among snapshots efficiently. Valuable snapshots can remain accessible or stored with faster access while less valuable snapshots are discarded or moved off-line. Measurements of the Thresher prototype indicate that the new techniques are efficient and scalable, imposing minimal (4%) performance penalty on expected common workloads. 1

“Time travel ” in the storage system is accessing past storage system states. Legacy application programs could run transparently over the past states if the past states were virtualized in a form that makes them look like the current state. There are many levels in the storage system at which past state virtualization could occur. How do we choose? We think that past state virtualization should occur at a high storage system buffer manager level, such as database buffer manager. Everything above this level can run legacy programs. The system below can manage the mechanisms needed to implement the virtualization. This approach can be applied to any kind of storage system, ranging from traditional databases and file systems to the new generation of specialized storage managers such as Bigtable. Granted

Abstract not found

Data Snapshot technology is a standard feature of modern storage systems. Most such systems use copy-on-write techniques to manage snapshot data in order to optimize storage space requirements for maintaining history data. Copy-on-write methods tend to write data out-of-place at a location which may be far away from the original location of the data on the disk. This phenomenon gradually leads to fragmentation of the ondisk snapshot data and degradation in the disk I/O performance. This work analyzes Logical Volume Manager’s (LVM2) snapshot technology and studies the effect of copyon-write on the on-disk placement of the snapshot data. Based on these findings, we propose new disk space allocation and data placement techniques for snapshot volumes in order to reduce physical distance between related blocks and improve disk access performance. A prototype is implemented and its performance is compared with the original LVM2 implementation in order to measure the effectiveness of the proposed schemes. The new schemes tend to perform better than the old LVM2 ranging from 18 % to 40 % at the cost of some performance penalty for first time writes in some cases. iii